Structured Failure Analysis of Autonomous Collaborative Platform Management

Abstract

Controlling multiple autonomous, uncrewed aircraft, or autonomous collaborative platforms (ACPs), during flight missions is a difficult multitasking effort. Due to the complexities and risks related to aircraft operations, it is imperative that the designs of emerging ACP management controls yield as few errors as possible during such missions. One way to achieve this is to examine, classify, and enumerate the types of errors that pilots make when flying missions with autonomous teammates. Here, we examine performance in a simulated piloting task in which individuals must direct four ACPs to eliminate ground targets while simultaneously piloting their own aircraft. We conducted structured failure analyses on different behavioral outcomes, integrating two different human factors taxonomies. The results of these analyses indicate that task failures were jointly attributable to cognitive capacity limits, configuration complexity, and ACP interface design.